数据状态
同步自 OpenRouter Providers · 101 家托管商 · source=openrouter · 2026-08-01T19:40:44.206Z
Together
总部 美国
19 模型24 端点日可用 96.5%
托管模型19
端点24
日可用率均96.5%
最低输入 $/M$0.050
最大上下文1.0M
托管端点 · 24
来自 OpenRouter 各模型 Endpoints API：同一模型可能有多量化 / 多区域端点。
| 模型 | Tag | 量化 | 上下文 | 输入 | 输出 | 5m | 30m | 1d | 延迟 | 吞吐 | 缓存 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| cogito-v2.1-671b deepcogito/cogito-v2.1-671b | together | — | 128k | $1.25 | $1.25 | — | — | 100.00% | — | — | — |
| gemma-3n-e4b-it google/gemma-3n-e4b-it | together | — | 33k | $0.060 | $0.120 | 100.00% | 100.00% | 100.00% | — | — | — |
| kimi-k2.7-code moonshotai/kimi-k2.7-code | together | — | 262k | $0.950 | $4.00 | — | — | 99.91% | — | — | — |
| qwen-2.5-7b-instruct qwen/qwen-2.5-7b-instruct | together/fp8 | fp8 | 33k | $0.300 | $0.300 | 100.00% | 99.94% | 99.9% | — | — | — |
| inkling-small thinkingmachines/inkling-small | together | — | 524k | $0.500 | $1.20 | — | 100.00% | 99.8% | — | — | — |
| kimi-k2.6 moonshotai/kimi-k2.6 | together | — | 262k | $1.20 | $4.50 | 100.00% | 100.00% | 99.7% | — | — | — |
| llama-guard-4-12b meta-llama/llama-guard-4-12b | together | — | 1.0M | $0.200 | $0.200 | 95.6% | 99.5% | 99.6% | — | — | — |
| minimax-m3 minimax/minimax-m3 | together | — | 524k | $0.300 | $1.20 | 97.5% | 96.1% | 99.4% | — | — | — |
| deepseek-v4-pro deepseek/deepseek-v4-pro | together | — | 512k | $1.74 | $3.48 | 100.00% | 99.0% | 98.7% | — | — | — |
| llama-3.3-70b-instruct meta-llama/llama-3.3-70b-instruct | together/fp8 | fp8 | 131k | $1.04 | $1.04 | 100.00% | 100.00% | 98.7% | — | — | — |
| gpt-oss-20b openai/gpt-oss-20b | together | — | 131k | $0.050 | $0.200 | — | — | 98.5% | — | — | — |
| gpt-oss-20b openai/gpt-oss-20b | together | — | 131k | $0.050 | $0.200 | — | — | 98.5% | — | — | — |
| nemotron-3-ultra-550b-a55b nvidia/nemotron-3-ultra-550b-a55b | together | — | 512k | $0.600 | $3.60 | 96.1% | 95.0% | 97.7% | — | — | — |
| nemotron-3-ultra-550b-a55b nvidia/nemotron-3-ultra-550b-a55b | together | — | 512k | $0.600 | $3.60 | 96.1% | 95.0% | 97.7% | — | — | — |
| qwen3.5-9b qwen/qwen3.5-9b | together | — | 262k | $0.170 | $0.250 | 100.00% | 100.00% | 97.0% | — | — | — |
| inkling thinkingmachines/inkling | together | — | 524k | $1.00 | $4.05 | 100.00% | 100.00% | 97.0% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | together | — | 262k | $0.280 | $0.860 | 86.2% | 95.6% | 96.1% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | together | — | 262k | $0.280 | $0.860 | 86.2% | 95.6% | 96.1% | — | — | — |
| glm-5.2 z-ai/glm-5.2 | together | — | 512k | $1.40 | $4.40 | 99.2% | 98.5% | 95.8% | — | — | — |
| gpt-oss-120b openai/gpt-oss-120b | together | — | 131k | $0.150 | $0.600 | 100.00% | 99.9% | 95.6% | — | — | — |
| kimi-k3 moonshotai/kimi-k3 | together | — | 1M | $3.00 | $15.0 | 96.6% | 97.7% | 94.2% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | together | — | 262k | $0.390 | $0.970 | 65.2% | 63.7% | 79.6% | — | — | — |
| gemma-4-31b-it google/gemma-4-31b-it | together | — | 262k | $0.390 | $0.970 | 65.2% | 63.7% | 79.6% | — | — | — |
| virtuoso-large arcee-ai/virtuoso-large | together | — | 131k | $0.750 | $1.20 | — | — | — | — | — | — |
覆盖模型 · 19
元数据与端点观测同步自 OpenRouter 公开 API。GrokCode 不做路由转发；自建测速请用 API 实验室。
站内推荐
同系工具：Clavue CLI / imux IDE / clavue-2.1
Clavue · CLI 与 Agent 平台
CLI / GUI Agent 运行时、设备登录、会员额度与 OpenAI 兼容 API（api.clavue.com）。开发脚本、CI 与本地工具一条链路。
打开 Clavue ↗imux · 原生 macOS AI IDE
Clavue 平台的原生 IDE：多 Agent 分屏、Ghostty 级终端、Agent Chat、浏览器自动化与 Supervisor——不是又一个 Electron 壳。
了解 imux ↗Clavue 2.1 · 产品级大模型
旗舰模型 clavue-2.1（及 fast / pro / rev）：适合复杂推理与长程 Agent 循环。Chat、imux、API 共用会员额度。
查看模型 ↗